A Sentiment-Aware Contextual Model for Real-Time Disaster Prediction Using Twitter Data
Open Access
- 25 June 2021
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 13 (7), 163
- https://doi.org/10.3390/fi13070163
Abstract
The massive amount of data generated by social media present a unique opportunity for disaster analysis. As a leading social platform, Twitter generates over 500 million Tweets each day. Due to its real-time characteristic, more agencies employ Twitter to track disaster events to make a speedy rescue plan. However, it is challenging to build an accurate predictive model to identify disaster Tweets, which may lack sufficient context due to the length limit. In addition, disaster Tweets and regular ones can be hard to distinguish because of word ambiguity. In this paper, we propose a sentiment-aware contextual model named SentiBERT-BiLSTM-CNN for disaster detection using Tweets. The proposed learning pipeline consists of SentiBERT that can generate sentimental contextual embeddings from a Tweet, a Bidirectional long short-term memory (BiLSTM) layer with attention, and a 1D convolutional layer for local feature extraction. We conduct extensive experiments to validate certain design choices of the model and compare our model with its peers. Results show that the proposed SentiBERT-BiLSTM-CNN demonstrates superior performance in the F1 score, making it a competitive model in Tweets-based disaster prediction.Keywords
This publication has 22 references indexed in Scilit:
- Deep Learning for Extreme Multi-label Text ClassificationPublished by Association for Computing Machinery (ACM) ,2017
- Event classification and location prediction from tweets during disastersAnnals of Operations Research, 2017
- Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNNExpert Systems with Applications, 2017
- Answering Twitter QuestionsPublished by Association for Computing Machinery (ACM) ,2016
- DeepMeSH: deep semantic representation for improving large-scale MeSH indexingBioinformatics, 2016
- Convolutional neural networks for biomedical text classificationPublished by Association for Computing Machinery (ACM) ,2015
- Weakly Supervised Extraction of Computer Security Events from TwitterPublished by Association for Computing Machinery (ACM) ,2015
- Think Local, Retweet GlobalPublished by Association for Computing Machinery (ACM) ,2015
- Using Social Media to Enhance Emergency Situation AwarenessIEEE Intelligent Systems, 2012
- Short text classification in twitter to improve information filteringPublished by Association for Computing Machinery (ACM) ,2010